Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

  • Add int8 scalar quantization to the HNSW vector format. This optionally allows for more compact lossy storage for the vectors, requiring about 75% memory for fast HNSW search.
  • HNSW graph now can be merged with multiple

  • thread
  • threads, leveraging the same infrastructure that inter-segment concurrency utilizes.

Improvements

  • Speed up Panama vector support, use FMA, and test improvements. 
  • FSTCompiler can now approximately limit how much RAM it uses to share suffixes share suffixes during FST construction using the suffixRAMLimitMB method. 

...